Providing normalised medical images

Abstract

: A computer-implemented method of providing normalised medical images ( 110′1 . . . n ) representing a region of interest ( 120 ) in a subject, is provided. The method includes: warping medical images ( 1101 . . . n ) in a temporal series to a 2D atlas image ( 130 ), to provide normalised medical images ( 110′1 . . . n ) having a warped region of interest ( 120′1 . . . n ) for comparison with the region of interest ( 120 ) in the atlas image ( 130 ). The method also includes outputting the normalised medical images ( 110′1 . . . n ), and/or outputting a magnitude of a change in the warped region of interest ( 120′1 . . . n ) between the normalised medical images ( 110′1 . . . n ).

1 . A computer-implemented method of providing normalised medical images representing a region of interest in a subject, the method comprising:
 receiving image data comprising a temporal series of 2D medical images including a region of interest in the subject;   receiving a 2D atlas image representing the region of interest; and for each medical image in the temporal series:
 warping the medical image to the atlas image, to provide a normalised medical image having a warped region of interest for comparison with the region of interest in the atlas image; and 
 outputting the normalised medical images and a magnitude of a change in the warped region of interest between the normalised medical images. 
   
     
     
         2 . The computer-implemented method according to  claim 1 , wherein the 2D atlas image represents a preferred perspective of the region of interest for assessing a medical condition in the temporal series of 2D medical images. 
     
     
         3 . The computer-implemented method according to  claim 1 , wherein the warping is based on a mapping between a plurality of corresponding landmarks represented in both the medical image and the atlas image. 
     
     
         4 . The computer-implemented method according to  claim 1 , wherein the atlas image comprises a plurality of labelled anatomical landmarks; and wherein the method further comprises:
 applying a feature detector to each medical image in the temporal series to identify a plurality of landmarks in the medical image that correspond to the labelled anatomical landmarks, wherein the mapping is determined using the identified corresponding landmarks.   
     
     
         5 . The computer-implemented method according to  claim 4 , wherein the applying a feature detector is performed using an edge detector, a model-based segmentation, or a neural network. 
     
     
         6 . The computer-implemented method according to  claim 1 , further comprising:
 adjusting an intensity of each medical image in the temporal series based on an intensity at one or more positions in the atlas image, based on an intensity at one or more positions in a medical image in the temporal series, or based on an intensity at one or more positions in a reference image, to provide adjusted intensity values in the normalised medical images; and   adjusting an intensity of each medical image in the temporal series using an image style transfer algorithm, to provide adjusted intensity values in the normalised medical images.   
     
     
         7 . The computer-implemented method according to  claim 6 , wherein the warping the medical image to the atlas image is performed prior to the adjusting an intensity of the medical image. 
     
     
         8 . The computer-implemented method according to  claim 6 , further comprising:
 calculating a magnitude of a change in the warped region of interest between the normalised medical images based on the adjusted intensity values in the normalised medical images, wherein the outputting a magnitude of a change in the warped region of interest between the normalised medical images comprises outputting the calculated magnitude of the change.   
     
     
         9 . The computer-implemented method according to  claim 6 , wherein:
 the adjusting an intensity of each medical image, in the temporal series based on an intensity at one or more positions in the atlas image, provides an adjusted intensity value at the corresponding one or more positions in the normalised medical image that is the same as the intensity value at the one or more positions in the atlas image; and   wherein the adjusting an intensity of each medical image in the temporal series based on an intensity at one or more positions in a medical image in the temporal series provides an adjusted intensity value at the corresponding one or more positions in the normalised medical image that is the same as the intensity value at the one or more positions in the medical image in the temporal series; and   wherein the adjusting an intensity of each medical image in the temporal series based on an intensity at one or more positions in a reference image provides an adjusted intensity value at the corresponding one or more positions in the normalised medical image that is the same as the intensity value at the one or more positions in the reference image.   
     
     
         10 . The computer-implemented method according to  claim 6 , wherein the adjusting an intensity of each medical image in the temporal series based on an intensity at one or more positions in the atlas image comprises:
 calculating an average intensity value within a portion of the atlas image; and   normalising the intensity values in each medical image in the temporal series using the average intensity value.   
     
     
         11 . The computer-implemented method according to  claim 6 , wherein the normalising the intensity values in each medical image in the temporal series using the average intensity value comprises mapping the intensity values within a corresponding portion of each medical image in the temporal series to the average intensity value within the portion of the atlas image. 
     
     
         12 . The computer-implemented method according to  claim 1 , further comprising:
 suppressing one or more image features outside the region of interest in the normalised medical images.   
     
     
         13 . The computer-implemented method according to  claim 12 , further comprising:
 identifying the region of interest in the atlas image;   mapping an outline of the region of interest from the atlas image to each of the normalised medical images; and   adjusting image intensity values in the normalised medical images outside the mapped outline to suppress the one or more image features outside the region of interest.   
     
     
         14 . The computer-implemented method according to  claim 1 , further comprising:
 performing a statistical analysis of image intensity values within the region of interest in the normalised medical image, wherein the outputting a magnitude of a change in the warped region of interest between the normalised medical images comprises:   outputting the result of the statistical analysis for the normalised medical images.   
     
     
         15 . The computer-implemented method according to  claim 14 , wherein the outputting the result of the statistical analysis for the normalised medical images comprises:
 displaying a spatial map of the statistical analysis as an overlay on one or more of the normalised medical images.   
     
     
         16 . The computer-implemented method according to  claim 1 , wherein the temporal series of 2D medical images comprise X-ray images or ultrasound images. 
     
     
         17 . The computer-implemented method according to  claim 1 , wherein the temporal series of 2D medical images comprise X-ray images generated by a mobile X-ray imaging system. 
     
     
         18 . The computer-implemented method according to  claim 1 , wherein the temporal series of 2D medical images represent a longitudinal study on the subject. 
     
     
         19 . A non-transitory computer-readable medium comprising executable instructions which, when executed by at least one processor, cause the at least one processor to perform a method for providing normalised medical images, the method comprising:
 receiving image data comprising a temporal series of 2D medical images including a region of interest in the subject;   receiving a 2D atlas image representing the region of interest; and for each medical image in the temporal series:
 warping the medical image to the atlas image to provide a normalised medical image having a warped region of interest for comparison with the region of interest in the atlas image; and 
 outputting the normalised medical images ( 110 ′ 1 . . . n ) and a magnitude of a change in the warped region of interest between the normalised medical images. 
   
     
     
         20 . A system for providing normalised medical images ( 110 ′ 1 . . . n ) representing a region of interest in a subject, the system comprising one or more processors configured to:
 receive image data comprising a temporal series of 2D medical images including a region of interest in the subject; 
 receive a 2D atlas image representing the region of interest; and 
 for each medical image in the temporal series:
 warp the medical image to the atlas image to provide a normalised medical image having a warped region of interest for comparison with the region of interest in the atlas image; and 
 output the normalised medical images and/or output a magnitude of a change in the warped region of interest between the normalised medical images.